TEmA-small

This model is a fine-tuned version of the LaBSE, which is specialized for sentence similarity tasks in Azerbaijan texts. It maps sentences and paragraphs to a 768-dimensional dense vector space, useful for tasks like clustering, semantic search, and more.

Benchmark Results

STS-Benchmark

Accuracy Results

• Cosine Distance: 96.63
• Manhattan Distance: 96.52
• Euclidean Distance: 96.57

Usage

from transformers import AutoTokenizer, AutoModel
import torch

# Mean Pooling - Take attention mask into account for correct averaging
def mean_pooling(model_output, attention_mask):
   token_embeddings = model_output[0] #First element of model_output contains all token embeddings
   input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
   return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)

# Function to normalize embeddings
def normalize_embeddings(embeddings):
   return embeddings / embeddings.norm(dim=1, keepdim=True)

# Sentences we want embeddings for
sentences = [
   "Bu xoşbəxt bir insandır",
   "Bu çox xoşbəxt bir insandır", 
   "Bu gün günəşli bir gündür"
]

# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('LocalDoc/TEmA-small')
model = AutoModel.from_pretrained('LocalDoc/TEmA-small')

# Tokenize sentences
encoded_input = tokenizer(sentences, padding=True, truncation=True, max_length=128, return_tensors='pt')

# Compute token embeddings
with torch.no_grad():
   model_output = model(**encoded_input)

# Perform pooling
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])

# Normalize embeddings
sentence_embeddings = normalize_embeddings(sentence_embeddings)

# Calculate cosine similarities
cosine_similarities = torch.nn.functional.cosine_similarity(
   sentence_embeddings[0].unsqueeze(0), 
   sentence_embeddings[1:], 
   dim=1
)

print("Cosine Similarities:")
for i, score in enumerate(cosine_similarities):
   print(f"Sentence 1 <-> Sentence {i+2}: {score:.4f}")